MiDA (version 0.1.2)

MiStatCount: FDR for microarray gene expression data

Description

Performs descriptive statistics and FDR (False Discovery Rate) test for microarray expression matrix

Usage

MiStatCount(Matrix, specimens)

Arguments

Matrix

numeric matrix of expression data where each row corresponds to a probe (gene, transcript), and each column correspondes to a specimen (patient).

specimens

factor vector with two levels specifying specimens in the columns of the Matrix.

Value

a data frame containing for each probe: mean and sd values for both groups, difference of means, p-value for T-test and q-value for FDR (False Discovery Rate) correction.

Details

This function takes matrix of expression data and performs T-test with FDR correction for two groups for each probe.

T-test is a two-sided, two-class with equal variances against the null hypothesis 'mean1=mean2' for each row. See rowttests for details.

References

Welch B.L.(1951) On the comparison of several mean values: an alternative approach. Biometrika 38, 330-336. https://doi.org/10.1093/biomet/38.3-4.330

See Also

rowttests

Examples

# NOT RUN {
data("IMexpression"); data("IMspecimen") # load data and specimen information
#sampling data and specimen information
ExpData<-MiDataSample(IMexpression, IMspecimen$diagnosis,"ebv", "norm")
Specimens<-MiSpecimenSample(IMspecimen$diagnosis, "ebv", "norm")
#Counting statistics
StatRes<-MiStatCount(ExpData, Specimens)
head(StatRes)

# }